1818
1919 ```bash
2020 kubectl create secret generic hf-token --from-literal=token=$HF_TOKEN # Your Hugging Face Token with access to the set of Llama models
21- kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/vllm/gpu-deployment.yaml
21+ kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/vllm/gpu-deployment.yaml
2222 ```
2323
2424--8<-- "site-src/_ includes/model-server-cpu.md"
2525
2626 ```bash
27- kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/vllm/cpu-deployment.yaml
27+ kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/vllm/cpu-deployment.yaml
2828 ```
2929
3030--8<-- "site-src/_ includes/model-server-sim.md"
3131
3232 ```bash
33- kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/vllm/sim-deployment.yaml
33+ kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/vllm/sim-deployment.yaml
3434 ```
3535
3636### Install the Inference Extension CRDs
3737
3838``` bash
39- kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.1 .0/manifests.yaml
39+ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.2 .0/manifests.yaml
4040```
4141
4242### Install the Gateway
@@ -115,7 +115,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
115115 Set the chart version and then select a tab to follow the provider-specific instructions.
116116
117117 ``` bash
118- export IGW_CHART_VERSION=v1.1 .0
118+ export IGW_CHART_VERSION=v1.2 .0
119119 ```
120120
121121--8<-- "site-src/_ includes/epp.md"
@@ -133,7 +133,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
133133 1. Deploy the Inference Gateway:
134134
135135 ```bash
136- kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/gke/gateway.yaml
136+ kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/gke/gateway.yaml
137137 ```
138138
139139 Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status:
@@ -146,7 +146,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
146146 1. Deploy the HTTPRoute:
147147
148148 ```bash
149- kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/gke/httproute.yaml
149+ kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/gke/httproute.yaml
150150 ```
151151
152152 1. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`:
@@ -195,7 +195,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
195195 1. Deploy the Inference Gateway:
196196
197197 ```bash
198- kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/agentgateway/gateway.yaml
198+ kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/agentgateway/gateway.yaml
199199 ```
200200
201201 Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status:
@@ -206,7 +206,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
206206 1. Deploy the HTTPRoute:
207207
208208 ```bash
209- kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/agentgateway/httproute.yaml
209+ kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/agentgateway/httproute.yaml
210210 ```
211211
212212 1. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`:
@@ -271,7 +271,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens
271271Deploy the sample InferenceObjective which allows you to specify priority of requests.
272272
273273 ``` bash
274- kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/inferenceobjective.yaml
274+ kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/inferenceobjective.yaml
275275 ```
276276
277277--8<-- "site-src/_ includes/test.md"
@@ -293,35 +293,35 @@ You have now deployed a basic Inference Gateway with a simple routing strategy.
293293
294294 ``` bash
295295 helm uninstall vllm-llama3-8b-instruct
296- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/inferenceobjective.yaml --ignore-not-found
297- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/vllm/cpu-deployment.yaml --ignore-not-found
298- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/vllm/gpu-deployment.yaml --ignore-not-found
299- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/vllm/sim-deployment.yaml --ignore-not-found
296+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/inferenceobjective.yaml --ignore-not-found
297+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/vllm/cpu-deployment.yaml --ignore-not-found
298+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/vllm/gpu-deployment.yaml --ignore-not-found
299+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/vllm/sim-deployment.yaml --ignore-not-found
300300 kubectl delete secret hf-token --ignore-not-found
301301 ```
302302
303303 1. Uninstall the Gateway API Inference Extension CRDs:
304304
305305 ` ` ` bash
306- kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.1 .0/manifests.yaml --ignore-not-found
306+ kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.2 .0/manifests.yaml --ignore-not-found
307307 ` ` `
308308
309309 1. Choose one of the following options to cleanup the Inference Gateway.
310310
311311=== " GKE"
312312
313313 ` ` ` bash
314- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/gke/gateway.yaml --ignore-not-found
315- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/gke/healthcheck.yaml --ignore-not-found
316- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/gke/gcp-backend-policy.yaml --ignore-not-found
317- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/gke/httproute.yaml --ignore-not-found
314+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/gke/gateway.yaml --ignore-not-found
315+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/gke/healthcheck.yaml --ignore-not-found
316+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/gke/gcp-backend-policy.yaml --ignore-not-found
317+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/gke/httproute.yaml --ignore-not-found
318318 ` ` `
319319
320320=== " Istio"
321321
322322 ` ` ` bash
323- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/istio/gateway.yaml --ignore-not-found
324- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/istio/httproute.yaml --ignore-not-found
323+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/istio/gateway.yaml --ignore-not-found
324+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/istio/httproute.yaml --ignore-not-found
325325 ` ` `
326326
327327 The following steps assume you would like to clean up ALL Istio resources that were created in this quickstart guide.
@@ -341,8 +341,8 @@ You have now deployed a basic Inference Gateway with a simple routing strategy.
341341=== " Kgateway"
342342
343343 ` ` ` bash
344- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/agentgateway/gateway.yaml --ignore-not-found
345- kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1 .0/config/manifests/gateway/agentgateway/httproute.yaml --ignore-not-found
344+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/agentgateway/gateway.yaml --ignore-not-found
345+ kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2 .0/config/manifests/gateway/agentgateway/httproute.yaml --ignore-not-found
346346 ` ` `
347347
348348 The following steps assume you would like to cleanup ALL Kgateway resources that were created in this quickstart guide.
0 commit comments